Equipment fault analysis system and method based on inspection analysis intelligent box

Abstract

The invention relates to the technical field of equipment fault analysis, and discloses an equipment fault analysis system and method based on an inspection analysis intelligent box. The preliminary judgment module is configured to set an inspection analysis period according to the real-time equipment data volume, judge whether the equipment is suspected to be abnormal or not according to the real-time equipment data, and mark the suspected abnormal equipment; the data arrangement module is configured to construct an equipment data sequence of the sensor according to the serial number of the sensor; the abnormality judgment module is configured to judge whether the suspected abnormal equipment is abnormal equipment or not according to the data difference value, and an abnormality index is obtained according to the data difference value; and the grade early warning module is configured to perform equipment fault grade early warning according to the fault index and adjust the inspection analysis period. According to the invention, real-time monitoring and intelligent analysis of the operation state of the equipment are realized, so that the efficiency and accuracy of equipment maintenance are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment failure analysis, and in particular to an equipment failure analysis system and method based on an inspection and analysis intelligent box. Background Art

[0002] With the continuous improvement of industrial automation and informatization levels, the stable operation of equipment plays a vital role in production efficiency and safety.

[0003] To ensure the proper functioning of equipment, traditional equipment maintenance methods rely primarily on regular inspections and manual judgment. This approach often suffers from low efficiency, long response times, and an inability to detect potential faults in a timely manner. With the advancement of sensor technology, data acquisition technology, and big data analysis, equipment fault analysis systems are gradually moving towards intelligent and automated systems.

[0004] Therefore, it is necessary to provide an equipment fault analysis system and method based on an inspection and analysis intelligent box to solve the problem that equipment maintenance in the prior art mainly relies on regular inspections and manual judgment, which is inefficient. Summary of the Invention

[0005] In view of this, the present invention proposes an equipment fault analysis system and method based on an inspection and analysis intelligent box, aiming to solve the problem in the prior art that equipment maintenance mainly relies on regular inspections and manual judgment, which is inefficient.

[0006] On the one hand, the present invention proposes an equipment fault analysis system based on an inspection and analysis intelligent box, comprising: a database construction module configured to preset a standard range of data for each device and establish a standard data database; A preliminary judgment module is configured to collect real-time device data obtained by sensors pre-deployed in the device, set an inspection and analysis cycle based on the amount of real-time device data, determine whether the device is suspected of being abnormal based on the real-time device data, and mark the suspected abnormal device; a data collating module configured to, when determining that a device is suspected of being abnormal, obtain device data of the device within a preset time period, obtain a sensor number of the device data, and construct a device data sequence of the sensor based on the sensor number; An abnormality determination module is configured to calculate the data difference between each data in the device data sequence and the standard range in the standard data database, determine whether the device suspected of abnormality is an abnormal device based on the data difference, and if it is an abnormal device, obtain an abnormality index based on the data difference; The level warning module is configured to obtain a fault index of the device according to each abnormality index of the same device, perform a device fault level warning according to the fault index, and adjust the inspection and analysis cycle.

[0007] Furthermore, when the database construction module is configured to preset a standard range of data for each device and establish a standard data database, it includes: Obtaining the installation location of a pre-deployed sensor, setting a standard range of device data according to the installation location, and binding the sensor to the standard range; A standard data database is established based on the standard range that each sensor is bound to.

[0008] Furthermore, the preliminary judgment module is configured to collect real-time device data obtained by sensors pre-deployed in the device, and to set the inspection and analysis cycle according to the amount of real-time device data, including: Comparing the real-time device data volume with the first preset data volume and the second preset data volume, the first preset data volume being smaller than the second preset data volume; If the real-time device data volume is less than the first preset data volume, the inspection and analysis period is the first period; If the real-time device data volume is greater than or equal to the first preset data volume and less than the second preset data volume, the inspection and analysis period is the second period; If the real-time device data volume is greater than or equal to the second preset data volume, the inspection and analysis period is the third period; The lengths of the inspection and analysis cycles are, from longest to shortest, the first cycle, the second cycle, and the third cycle.

[0009] Furthermore, the preliminary judgment module is configured to judge whether a device is suspected of being abnormal based on the real-time device data and mark the suspected abnormal device, including: Comparing the real-time device data with the standard range corresponding to the sensor, and if the real-time device data is within the standard range, determining that the device is not a suspected abnormal device; If the real-time device data is not within the standard range, the device is determined to be a suspected abnormal device.

[0010] Furthermore, the data sorting module is configured to, when determining that a device is suspected of being abnormal, obtain device data of the device within a preset time period, obtain a sensor number of the device data, and construct a device data sequence of the sensor according to the sensor number, including: The preset duration includes several inspection and analysis cycles; The device data is classified according to the sensor number, and a device data sequence of the sensor is constructed according to the classification result.

[0011] Furthermore, the abnormality determination module is configured to calculate the data difference between each data in the device data sequence and the standard range in the standard data database based on the device data sequence, and determine whether the suspected abnormal device is an abnormal device based on the data difference, including: Calculating the difference between each data in the device data sequence and the data in the standard range; Setting a data difference threshold, and if there is a data difference value greater than or equal to the data difference threshold, determining that the suspected abnormal device is an abnormal device; If the data difference values ​​are all smaller than the data difference threshold, it is determined that the suspected abnormal device is not an abnormal device.

[0012] Furthermore, the abnormality determination module is configured to, if it is an abnormal device, obtain an abnormality index based on the data difference, including: Obtain the data difference of the same sensor of the abnormal device and filter out the largest data difference; Setting a difference judgment interval, if the maximum data difference is less than the minimum value of the difference judgment interval, the abnormality index is the first index; If the maximum data difference is within the difference judgment interval, the abnormality judgment index is the second index; If the maximum data difference is greater than the maximum value of the difference judgment interval, the abnormality judgment index is the third index.

[0013] Furthermore, when the level warning module is configured to obtain the fault index of the device according to each abnormality index of the same device, it includes: The fault index is the weighted sum of the abnormality indices in the same device.

[0014] Furthermore, when the level warning module is configured to issue a warning of the equipment fault level according to the fault index and adjust the inspection and analysis period, it includes: Setting a first warning index and a second warning index, wherein the first warning index is less than the second warning index; If the fault index is less than the first warning index, a first-level warning is issued to the device, and the inspection and analysis period is adjusted by a first adjustment coefficient; If the fault index is greater than or equal to the first warning index and less than the second warning index, a second-level warning is issued to the device, and the inspection and analysis period is adjusted by a second adjustment coefficient; If the fault index is greater than the second warning index, a third-level warning is issued to the device, and the inspection and analysis period is adjusted by a third adjustment coefficient; Among them, the warning levels from low to high are level one warning, level two warning and level three warning; the adjustment coefficient value range is 1> first adjustment coefficient> second adjustment coefficient> third adjustment coefficient> 0, and the inspection and analysis cycle after adjustment is the product of the inspection and analysis cycle before adjustment and the adjustment coefficient.

[0015] Compared to existing technologies, the present invention offers the following advantages: its modular design enables real-time monitoring and intelligent analysis of equipment operating status, thereby improving the efficiency and accuracy of equipment maintenance. First, the database construction module provides a solid foundation for the system. By presetting standard ranges for each device's data and establishing a standard data database, it provides a reference standard for subsequent analysis, ensuring accuracy and reliability. The preliminary assessment module collects real-time data from sensors within the equipment and sets inspection and analysis cycles based on this data, promptly identifying and flagging suspected abnormal equipment conditions. This process significantly shortens fault detection time, facilitates preventative maintenance, and avoids production interruptions or safety incidents caused by equipment failures. When a suspected abnormality occurs, the data collation module captures detailed data from the equipment over a preset period of time and constructs a data sequence, providing rich data support for in-depth analysis of the equipment's status. The anomaly determination module accurately determines whether an equipment abnormality has occurred by calculating the difference between the data sequence and the standard data, and then generates an anomaly index, providing clear guidance for maintenance personnel. Finally, the graded warning module calculates the equipment's failure index based on the anomaly index and issues a graded warning. This not only notifies relevant personnel to take timely action but also adjusts inspection and analysis cycles based on the failure index, enabling dynamic management and optimizing the allocation of maintenance resources. Overall, this system, through intelligent analysis and early warning mechanisms, effectively reduces equipment failure rates, extends equipment life, improves production efficiency, and reduces maintenance costs.

[0016] On the other hand, the present application also provides a device fault analysis method based on a patrol analysis smart box, comprising: Preset the standard range of each device data and establish a standard data database; Collect real-time device data obtained by sensors pre-installed in the equipment, set an inspection and analysis cycle based on the amount of real-time device data, determine whether the equipment is suspected of abnormality based on the real-time device data, and mark the suspected abnormal equipment; When it is determined that the device is suspected of being abnormal, the device data within a preset time period is obtained, and the sensor number of the device data is obtained, and the device data sequence of the sensor is constructed according to the sensor number; Calculate the data difference between each data in the device data sequence and the standard range in the standard data database according to the data difference, determine whether the suspected abnormal device is an abnormal device according to the data difference, and if it is an abnormal device, obtain an abnormality index according to the data difference; According to each abnormal index of the same device, a fault index of the device is obtained, and according to the fault index, a device fault level warning is performed and the inspection and analysis cycle is adjusted.

[0017] It can be understood that the equipment fault analysis system and method based on the inspection and analysis smart box provided in this application have the same beneficial effects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings: Figure 1 A functional block diagram of an equipment fault analysis system based on an inspection and analysis intelligent box provided by an embodiment of the present invention; Figure 2 This is a flow chart of a device fault analysis method based on an inspection and analysis intelligent box provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0020] In some embodiments of the present application, see Figure 1 As shown, this embodiment provides an equipment fault analysis system based on a patrol and analysis intelligent box, including: a database construction module configured to preset a standard range of data for each device and establish a standard data database; A preliminary judgment module is configured to collect real-time device data obtained by sensors pre-deployed in the device, set an inspection and analysis cycle based on the amount of real-time device data, determine whether the device is suspected of being abnormal based on the real-time device data, and mark the suspected abnormal device; a data collating module configured to, when determining that a device is suspected of being abnormal, obtain device data of the device within a preset time period, obtain a sensor number of the device data, and construct a device data sequence of the sensor based on the sensor number; An abnormality determination module is configured to calculate the data difference between each data in the device data sequence and the standard range in the standard data database, determine whether the device suspected of abnormality is an abnormal device based on the data difference, and if it is an abnormal device, obtain an abnormality index based on the data difference; The level warning module is configured to obtain a fault index of the device according to each abnormality index of the same device, perform a device fault level warning according to the fault index, and adjust the inspection and analysis cycle.

[0021] As can be appreciated, the modular design of the present invention enables real-time monitoring and intelligent analysis of equipment operating status, thereby improving the efficiency and accuracy of equipment maintenance. First, the database construction module provides a solid foundation for the system. By presetting standard ranges for each device's data and establishing a standard data database, it provides a reference standard for subsequent analysis, ensuring accuracy and reliability. The preliminary judgment module collects real-time data from the device's sensors and sets inspection and analysis cycles based on this data. This allows for the timely detection and flagging of suspected equipment anomalies. This process significantly shortens fault detection time, facilitates preventative maintenance, and avoids production interruptions or safety incidents caused by equipment failures. When a suspected anomaly occurs, the data collation module captures detailed data from the device over a preset period of time and constructs a data sequence, providing rich data support for in-depth analysis of the device's status. The anomaly determination module accurately determines whether an equipment anomaly has occurred by calculating the difference between the data sequence and the standard data, and then generates an anomaly index, providing a clear guide for maintenance personnel. Finally, the graded warning module calculates the equipment's failure index based on the anomaly index and issues a graded warning. This not only notifies relevant personnel to take timely action but also adjusts inspection and analysis cycles based on the failure index, enabling dynamic management and optimizing the allocation of maintenance resources. Overall, this system, through intelligent analysis and early warning mechanisms, effectively reduces equipment failure rates, extends equipment life, improves production efficiency, and reduces maintenance costs.

[0022] In some embodiments of the present application, when the database construction module is configured to preset a standard range of each device data and establish a standard data database, it includes: Obtaining the installation location of a pre-deployed sensor, setting a standard range of device data according to the installation location, and binding the sensor to the standard range; A standard data database is established based on the standard range that each sensor is bound to.

[0023] As you can see, the database construction module effectively manages and analyzes device data by presetting standard ranges for each device's data and establishing a standard data database. First, by obtaining the installation locations of pre-deployed sensors, the system can set standard ranges for device data based on these locations, ensuring data accuracy and relevance. Then, binding sensors to corresponding standard ranges ensures targeted and efficient data collection. Finally, the standard data database established based on the standard ranges bound to each sensor provides a solid foundation for subsequent data analysis and decision-making. This configuration not only improves data processing efficiency but also enhances data reliability and application flexibility, playing a vital role in device monitoring and maintenance.

[0024] In some embodiments of the present application, the preliminary judgment module is configured to collect real-time device data obtained by sensors pre-deployed in the device, and when setting the inspection and analysis cycle according to the amount of real-time device data, it includes: Comparing the real-time device data volume with the first preset data volume and the second preset data volume, the first preset data volume being smaller than the second preset data volume; If the real-time device data volume is less than the first preset data volume, the inspection and analysis period is the first period; If the real-time device data volume is greater than or equal to the first preset data volume and less than the second preset data volume, the inspection and analysis period is the second period; If the real-time device data volume is greater than or equal to the second preset data volume, the inspection and analysis period is the third period; The lengths of the inspection and analysis cycles are, from longest to shortest, the first cycle, the second cycle, and the third cycle.

[0025] It can be understood that, firstly, the present invention can achieve a reasonable allocation of resources. When the amount of real-time device data is small, that is, less than the first preset data amount, a longer first cycle is set for inspection and analysis, which avoids the waste of manpower and material resources caused by frequent inspections, so that resources can be concentrated in places where they are more needed. Secondly, the pertinence and efficiency of inspections are improved. If the amount of real-time device data is in different intervals, corresponding to inspection cycles of different lengths, such as if the data amount is between the first preset data amount and the second preset data amount, the second cycle is used; if the data amount is greater than or equal to the second preset data amount, a shorter third cycle is used. In this way, by setting the inspection frequency according to the data amount, possible problems with the equipment can be discovered in a timely manner, and timely responses and processing can be carried out to ensure the stable operation of the equipment. Overall, in this way, while ensuring the stable operation of the equipment, the utilization of inspection resources is optimized, and the scientificity and effectiveness of operation and maintenance management are improved.

[0026] In some embodiments of the present application, the preliminary judgment module is configured to judge whether a device is suspected of being abnormal based on the real-time device data and mark the suspected abnormal device, including: Comparing the real-time device data with the standard range corresponding to the sensor, and if the real-time device data is within the standard range, determining that the device is not a suspected abnormal device; If the real-time device data is not within the standard range, the device is determined to be a suspected abnormal device.

[0027] In some embodiments of the present application, the data sorting module is configured to, when determining that a device is suspected of being abnormal, obtain device data from the device within a preset time period, obtain a sensor number for the device data, and construct a device data sequence for the sensor based on the sensor number, including: The preset duration includes several inspection and analysis cycles; The device data is classified according to the sensor number, and a device data sequence of the sensor is constructed according to the classification result.

[0028] In some embodiments of the present application, the abnormality determination module is configured to calculate, based on the device data sequence, the data difference between each data in the sequence and the standard range in the standard data database, and determine whether the suspected abnormal device is an abnormal device based on the data difference, including: Calculating the difference between each data in the device data sequence and the data in the standard range; Setting a data difference threshold, and if there is a data difference value greater than or equal to the data difference threshold, determining that the suspected abnormal device is an abnormal device; If the data difference values ​​are all smaller than the data difference threshold, it is determined that the suspected abnormal device is not an abnormal device.

[0029] It will be appreciated that in the embodiments of the present application, the collaborative work of the preliminary judgment module, the data collation module, and the anomaly determination module enables effective real-time monitoring of the device's operating status and anomaly detection, thereby improving the device's operational efficiency and safety. The preliminary judgment module quickly identifies suspected anomaly devices by comparing real-time device data with the standard range. This not only improves the efficiency of anomaly detection but also reduces misidentification of normal devices. By marking suspected anomaly devices, further data analysis can be carried out in a targeted manner, saving resources and increasing processing speed. After a suspected anomaly device is marked, the data collation module acquires device data over a preset period of time and constructs a device data sequence based on the sensor number, providing a detailed data foundation for subsequent anomaly determination. This data sequence construction method facilitates analysis of device operating trends over a period of time, leading to more accurate judgment of the device's operating status. Furthermore, classifying data by sensor number facilitates rapid identification of the source of problems and provides guidance for maintenance and repair. The anomaly determination module determines whether a suspected anomaly device is truly an anomaly by calculating the difference between each data point in the device data sequence and the standard range in the standard data database and setting a data difference threshold. This method not only improves the accuracy of anomaly determination, but also provides flexibility and adaptability for anomaly determination by setting thresholds. When there is a data difference that exceeds the threshold, measures can be taken quickly to prevent potential equipment failures or production accidents, thereby ensuring the stable operation of the equipment and production safety. In summary, the embodiments of the present application achieve efficient monitoring of the equipment operating status and accurate anomaly determination through a series of modular processing flows.

[0030] In some embodiments of the present application, the abnormality determination module is configured to, if the device is abnormal, obtain an abnormality index based on the data difference, including: Obtain the data difference of the same sensor of the abnormal device and filter out the largest data difference; Setting a difference judgment interval, if the maximum data difference is less than the minimum value of the difference judgment interval, the abnormality index is the first index; If the maximum data difference is within the difference judgment interval, the abnormality judgment index is the second index; If the maximum data difference is greater than the maximum value of the difference judgment interval, the abnormality judgment index is the third index.

[0031] In some embodiments of the present application, when the level warning module is configured to obtain a fault index of a device based on each abnormality index of the same device, the following steps are included: The fault index is the weighted sum of the abnormality indices in the same device.

[0032] It will be appreciated that in the embodiments of the present application, the anomaly determination module, by acquiring data differences from the same sensor and selecting the maximum data difference, allows the system to quickly identify the most significant anomaly signals. This helps prioritize those anomalies most likely to impact the normal operation of the device. Secondly, by setting a difference determination interval and determining an anomaly index based on the relative position of the maximum data difference within that interval, the system can preliminarily categorize the severity of the anomaly. This categorization facilitates rapid response decisions. For example, if the maximum data difference is less than the minimum value of the difference determination interval, the device anomaly can be considered to be of low severity, leading to the implementation of lower-level warning measures. Conversely, if the maximum data difference is greater than the maximum value of the difference determination interval, it indicates a severe anomaly and requires immediate action. Furthermore, the graded warning module calculates a fault index by weighted summation of each anomaly index for the same device, providing a comprehensive assessment of the device's health. This weighted summation approach allows for flexible adjustment of the impact of the fault index based on different anomalies, thereby providing more accurate fault prediction and warning. For example, certain anomaly indicators may have a greater impact on the normal operation of the device and, therefore, may be assigned a higher weight when calculating the fault index. Overall, this abnormality judgment and graded warning mechanism not only improves the efficiency of abnormality detection, but also makes equipment maintenance and fault handling more orderly and efficient through graded processing and comprehensive evaluation. It not only helps to reduce equipment downtime and improve production efficiency, but also extends the service life of equipment and reduces maintenance costs.

[0033] In some embodiments of the present application, when the level warning module is configured to issue a warning of the equipment fault level according to the fault index and adjust the inspection and analysis period, it includes: Setting a first warning index and a second warning index, wherein the first warning index is less than the second warning index; If the fault index is less than the first warning index, a first-level warning is issued to the device, and the inspection and analysis period is adjusted by a first adjustment coefficient; If the fault index is greater than or equal to the first warning index and less than the second warning index, a second-level warning is issued to the device, and the inspection and analysis period is adjusted by a second adjustment coefficient; If the fault index is greater than the second warning index, a third-level warning is issued to the device, and the inspection and analysis period is adjusted by a third adjustment coefficient; Among them, the warning levels from low to high are level one warning, level two warning and level three warning; the adjustment coefficient value range is 1> first adjustment coefficient> second adjustment coefficient> third adjustment coefficient> 0, and the inspection and analysis cycle after adjustment is the product of the inspection and analysis cycle before adjustment and the adjustment coefficient.

[0034] It will be appreciated that in some embodiments of the present application, the hierarchical warning module, by setting a first warning index and a second warning index, can provide graded warnings based on the device's fault index, providing maintenance personnel with a clear indication of fault severity. When the fault index is less than the first warning index, the device is at a certain risk. In this case, a first-level warning is issued and the inspection and analysis cycle is appropriately adjusted to avoid unnecessary frequent inspections, thereby saving resources and time. When the fault index is between the first and second warning indices, a second-level warning is issued, indicating that the device may be at a potential risk. In this case, the inspection cycle is adjusted using the second adjustment coefficient to promptly detect and address potential issues and prevent failures. If the fault index is greater than the second warning index, a third-level warning is issued, indicating that the device is at a serious risk of failure. In this case, the third adjustment coefficient is used to perform the most frequent inspections to ensure safe and stable operation of the device. In addition, by setting different adjustment coefficients, the system can flexibly adjust the inspection and analysis cycle, making maintenance work more efficient and targeted. The adjustment coefficient ranges from 1 to 0, ensuring that the inspection cycle is neither too loose, resulting in failures, nor too frequent, resulting in resource waste. This dynamic adjustment mechanism allows maintenance work to be optimized based on the actual operating conditions of the equipment, thereby extending equipment life, reducing maintenance costs, and improving overall production efficiency. In summary, the hierarchical warning module, through graded warnings and dynamic adjustment of inspection cycles, not only improves the efficiency and accuracy of equipment maintenance, but also optimizes resource allocation, reduces operating costs, and ultimately improves the reliability of the entire system.

[0035] On the other hand, see Figure 2 As shown, the present application also provides a device fault analysis method based on a patrol inspection and analysis smart box, which is applied to the above-mentioned device fault analysis system based on a patrol inspection and analysis smart box, including the following steps: S100, presetting the standard range of each device data and establishing a standard data database; S200: Collecting real-time device data acquired by pre-installed sensors in the device, setting an inspection and analysis cycle based on the amount of real-time device data, determining whether the device is suspected of being abnormal based on the real-time device data, and marking the suspected abnormal device; S300: When it is determined that the device is suspected of being abnormal, obtain device data of the device within a preset time period, obtain a sensor number of the device data, and construct a device data sequence of the sensor according to the sensor number; S400: Calculate the data difference between each data in the device data sequence and the standard range in the standard data database, determine whether the suspected abnormal device is an abnormal device based on the data difference, and if it is an abnormal device, obtain an abnormality index based on the data difference; S500 , obtaining a fault index of the device according to each abnormality index of the same device, performing a device fault level warning according to the fault index, and adjusting the inspection and analysis cycle.

[0036] As can be appreciated, the present invention improves the efficiency and accuracy of equipment maintenance. First, by presetting standard ranges for each device's data and establishing a standard data database (S100), a benchmark is provided for subsequent fault analysis. This step ensures that all device data comparisons are based on a unified standard, thereby improving the accuracy and reliability of the analysis. Second, by collecting real-time device data from pre-installed sensors within the equipment and setting inspection and analysis cycles based on this data (S200), the equipment's status can be monitored in real time, allowing for the timely detection of abnormalities. This approach not only improves the timeliness of fault detection but also reduces production losses and safety incidents caused by equipment failures. When a device is suspected of an abnormality, by acquiring device data for a preset period of time and constructing a device data sequence (S300), detailed analysis of the device's operating trends and historical performance can be performed. This helps to more accurately identify the nature and cause of the fault, enabling more effective repair measures. By calculating the difference between the device data sequence and the standard data and determining whether the device is abnormal based on this difference (S400), the device's operating status can be quantified, providing data support for decision-making. The introduction of an abnormality index quantifies the severity of the fault, thereby providing priority for equipment maintenance and repair. Finally, by calculating the equipment's failure index and performing equipment failure level warnings and adjustments to the inspection and analysis cycle (S500), dynamic management of equipment maintenance can be achieved. This method not only provides timely warnings of potential failure risks, but also allows for flexible adjustments to maintenance strategies based on the equipment's actual operating conditions, thereby optimizing the allocation of maintenance resources and improving the equipment's operating efficiency and lifespan. In summary, the equipment failure analysis method provided in this application significantly improves the efficiency and accuracy of equipment failure analysis through standardization, real-time monitoring, historical data analysis, quantitative evaluation, and dynamic management, and has important practical application value for ensuring stable equipment operation and reducing maintenance costs.

[0037] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0038] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0039] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0040] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. An equipment fault analysis system based on an inspection and analysis intelligent box, characterized in that: include: a database construction module configured to preset a standard range of data for each device and establish a standard data database; A preliminary judgment module is configured to collect real-time device data obtained by sensors pre-deployed in the device, set an inspection and analysis cycle based on the amount of real-time device data, determine whether the device is suspected of being abnormal based on the real-time device data, and mark the suspected abnormal device; a data collating module configured to, when determining that a device is suspected of being abnormal, obtain device data of the device within a preset time period, obtain a sensor number of the device data, and construct a device data sequence of the sensor based on the sensor number; An abnormality determination module is configured to calculate the data difference between each data in the device data sequence and the standard range in the standard data database, determine whether the device suspected of abnormality is an abnormal device based on the data difference, and if it is an abnormal device, obtain an abnormality index based on the data difference; The level warning module is configured to obtain a fault index of the device according to each abnormality index of the same device, perform a device fault level warning according to the fault index, and adjust the inspection and analysis cycle.

2. The equipment failure analysis system based on the inspection and analysis intelligent box according to claim 1 is characterized in that: When the database construction module is configured to preset a standard range of data for each device and establish a standard data database, it includes: Obtaining the installation location of a pre-deployed sensor, setting a standard range of device data according to the installation location, and binding the sensor to the standard range; A standard data database is established based on the standard range that each sensor is bound to.

3. The equipment failure analysis system based on the inspection and analysis intelligent box according to claim 1 is characterized in that: The preliminary judgment module is configured to collect real-time device data obtained by sensors pre-deployed in the device, and to set an inspection and analysis cycle according to the amount of real-time device data, including: Comparing the real-time device data volume with the first preset data volume and the second preset data volume, the first preset data volume being smaller than the second preset data volume; If the real-time device data volume is less than the first preset data volume, the inspection and analysis period is the first period; If the real-time device data volume is greater than or equal to the first preset data volume and less than the second preset data volume, the inspection and analysis period is the second period; If the real-time device data volume is greater than or equal to the second preset data volume, the inspection and analysis period is the third period; The lengths of the inspection and analysis cycles are, from longest to shortest, the first cycle, the second cycle, and the third cycle.

4. The equipment failure analysis system based on the inspection and analysis intelligent box according to claim 1 is characterized in that: The preliminary judgment module is configured to judge whether a device is suspected of being abnormal based on the real-time device data and mark the device suspected of being abnormal, including: Comparing the real-time device data with the standard range corresponding to the sensor, and if the real-time device data is within the standard range, determining that the device is not a suspected abnormal device; If the real-time device data is not within the standard range, the device is determined to be a suspected abnormal device.

5. The equipment failure analysis system based on the inspection and analysis intelligent box according to claim 4 is characterized in that: The data sorting module is configured to, when determining that a device is suspected of being abnormal, obtain device data of the device within a preset time period, obtain a sensor number of the device data, and construct a device data sequence of the sensor according to the sensor number, including: The preset duration includes several inspection and analysis cycles; The device data is classified according to the sensor number, and a device data sequence of the sensor is constructed according to the classification result.

6. The equipment failure analysis system based on the inspection and analysis intelligent box according to claim 5 is characterized in that: The abnormality determination module is configured to calculate the data difference between each data in the device data sequence and the standard range in the standard data database according to the device data sequence, and determine whether the suspected abnormal device is an abnormal device according to the data difference, including: Calculating the difference between each data in the device data sequence and the data in the standard range; Setting a data difference threshold, and if there is a data difference value greater than or equal to the data difference threshold, determining that the suspected abnormal device is an abnormal device; If the data difference values ​​are all smaller than the data difference threshold, it is determined that the suspected abnormal device is not an abnormal device.

7. The equipment failure analysis system based on the inspection and analysis intelligent box according to claim 6 is characterized in that: The abnormality determination module is configured to, if the device is abnormal, obtain an abnormality index based on the data difference, including: Obtain the data difference of the same sensor of the abnormal device and filter out the largest data difference; Setting a difference judgment interval, if the maximum data difference is less than the minimum value of the difference judgment interval, the abnormality index is the first index; If the maximum data difference is within the difference judgment interval, the abnormality judgment index is the second index; If the maximum data difference is greater than the maximum value of the difference judgment interval, the abnormality judgment index is the third index.

8. The equipment failure analysis system based on the inspection and analysis intelligent box according to claim 7 is characterized in that: When the level warning module is configured to obtain the fault index of the device according to each abnormality index of the same device, it includes: The fault index is the weighted sum of the abnormality indices in the same device.

9. The equipment failure analysis system based on the inspection and analysis intelligent box according to claim 8 is characterized in that: When the level warning module is configured to issue a warning of the equipment fault level according to the fault index and adjust the inspection and analysis period, it includes: Setting a first warning index and a second warning index, wherein the first warning index is less than the second warning index; If the fault index is less than the first warning index, a first-level warning is issued to the device, and the inspection and analysis period is adjusted by a first adjustment coefficient; If the fault index is greater than or equal to the first warning index and less than the second warning index, a second-level warning is issued to the device, and the inspection and analysis period is adjusted by a second adjustment coefficient; If the fault index is greater than the second warning index, a third-level warning is issued to the device, and the inspection and analysis period is adjusted by a third adjustment coefficient; Among them, the warning levels from low to high are level one warning, level two warning and level three warning; the adjustment coefficient value range is 1> first adjustment coefficient> second adjustment coefficient> third adjustment coefficient> 0, and the inspection and analysis cycle after adjustment is the product of the inspection and analysis cycle before adjustment and the adjustment coefficient.

10. A device fault analysis method based on a patrol inspection and analysis smart box, applied to the device fault analysis system based on a patrol inspection and analysis smart box according to any one of claims 1 to 9, characterized in that: include: Preset the standard range of each device data and establish a standard data database; Collect real-time device data obtained by sensors pre-installed in the equipment, set an inspection and analysis cycle based on the amount of real-time device data, determine whether the equipment is suspected of abnormality based on the real-time device data, and mark the suspected abnormal equipment; When it is determined that the device is suspected of being abnormal, the device data within a preset time period is obtained, and the sensor number of the device data is obtained, and the device data sequence of the sensor is constructed according to the sensor number; Calculate the data difference between each data in the device data sequence and the standard range in the standard data database according to the data difference, determine whether the suspected abnormal device is an abnormal device according to the data difference, and if it is an abnormal device, obtain an abnormality index according to the data difference; According to each abnormal index of the same device, a fault index of the device is obtained, and according to the fault index, a device fault level warning is performed and the inspection and analysis cycle is adjusted.

Images